* Initial implementation of Ollama as a service * Fix model selector in tool window * Enable image attachment * Rewrite OllamaSettingsForm in Kt * Create OllamaInlineCompletionModel and use it for building completion template * Add support for blocking code completion on models that we don't know support it * Allow disabling code completion settings * Disable code completion settings when an unsupported model is entered * Track FIM template in settings as a derived state * Update llm-client * Initial implementation of model combo box * Add Ollama icon and display models as list * Make OllamaSettingsState immutable & convert OllamaSettings to Kotlin * Add refresh models button * Distinguish between empty/needs refresh/loading * Avoid storing any model if the combo box is empty * Fix icon size * Back to mutable settings There were some bugs with immutable settings * Store available models in settings state * Expose available models in model dropdown * Add dark icon * Cleanups for CompletionRequestProvider * Fix checkstyle issues * refactor: migrate to SimplePersistentStateComponent * fix: add code completion stop tokens * fix: display only one item in the model popup action group * fix: add back multi model selection --------- Co-authored-by: Carl-Robert Linnupuu <carlrobertoh@gmail.com> |
||
|---|---|---|
| .github | ||
| buildSrc | ||
| codegpt-telemetry | ||
| codegpt-treesitter | ||
| config/checkstyle | ||
| gradle | ||
| src | ||
| .gitattributes | ||
| .gitignore | ||
| .gitmodules | ||
| build.gradle.kts | ||
| CHANGELOG.md | ||
| codestyle.xml | ||
| DESCRIPTION.md | ||
| GETTING_STARTED.md | ||
| gradle-win-arm64.properties | ||
| gradle.properties | ||
| gradlew | ||
| gradlew.bat | ||
| LICENSE | ||
| README.md | ||
| settings.gradle.kts | ||
CodeGPT
A JetBrains extension providing access to state-of-the-art LLMs, such as GPT-4, Claude 3, Code Llama, and others, all for free
Table of Contents
About The Project
CodeGPT is your go-to AI coding assistant, offering assistance throughout your entire software development journey while keeping privacy in mind. Access state-of-the-art large language models from leading providers such as OpenAI, Anthropic, Azure, Mistral, and others, or connect to a locally hosted model for a completely offline and transparent development experience.
Core Features
Leveraging large language models, CodeGPT offers a wide range of features to enhance your coding experience, including, but not limited to:
Code Completions
Receive single-line or whole-function autocomplete suggestions as you type.
Note
: Currently only supported with OpenAI, Custom OpenAI, or LLaMA.
Chat (with Vision)
Get instant coding advice through a ChatGPT-like interface. Ask questions, seek explanations, or get guidance on your projects without leaving your IDE.
CodeGPT also supports vision models and image understanding, allowing you to attach images for more context-aware assistance. It can detect new screenshots automatically, saving you time by eliminating the need to manually upload images each time you take a screenshot.
Commit Message Generation
CodeGPT can generate meaningful commit messages based on the changes made in your codebase. It analyzes the diff of your staged changes and suggests concise and descriptive commit messages, saving you time and effort.
Reference Files
CodeGPT allows you to reference specific files or documentation during your chat sessions, ensuring that responses are always relevant and accurate.
Name Suggestions
Stuck on naming a method or variable? CodeGPT offers context-aware suggestions, helping you adhere to best practices and maintain readability in your codebase.
OpenAI Compatibility
Interested in trying out 800t/s or getting access to new models as soon as they're released? We provide integration with most cloud providers that are OpenAI-compatible, such as Together.ai, Grok, Anyscale, and others, as well as the option to customize your own setup.
Offline Development Support
CodeGPT supports a completely offline development workflow by allowing you to connect to a locally hosted language model. This ensures that your code and data remain private and secure within your local environment, eliminating the need for an internet connection or sharing sensitive information with third-party servers.
Running locally
Linux or macOS
git clone https://github.com/carlrobertoh/CodeGPT.git
cd CodeGPT
git submodule update
./gradlew runIde
Windows ARM64
./gradlew runIde -Penv=win-arm64
Tailing logs
tail -f build/idea-sandbox/system/log/idea.log
Privacy
Your data stays yours. CodeGPT does not collect or store any kind of sensitive information.
However, with users' consent, we do collect anonymous usage data, which we use to understand how users interact with the extension, including the most-used features and preferred providers.
Feedback
Your input helps us grow. Reach out through:
License
Apache 2.0 © Carl-Robert Linnupuu
If you found this project interesting, kindly rate it on the marketplace and don't forget to give it a star. Thanks again!






